Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 23802
    Prev
    Next
    INDEX
    Explanations

    URLs and resource identifiers related to Android code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cken
    -0.17
    skirts
    -0.16
    _lb
    -0.15
    akening
    -0.15
    ackle
    -0.15
    geh
    -0.15
    anner
    -0.15
    rique
    -0.14
    FB
    -0.14
    æ³Ĭ
    -0.14
    POSITIVE LOGITS
    +xml
    0.17
    .xml
    0.16
     Rounds
    0.15
     Hib
    0.15
    strict
    0.15
    ÏģιÏĥ
    0.14
     Exped
    0.14
    xml
    0.14
     Cro
    0.14
    âĢĮâĢĮ
    0.14
    Activations Density 0.003%

    No Known Activations